8.8

CVE-2026-27893: vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

Modified
AliasesGHSA-7972-pg2x-xr59PYSEC-2026-2297CGA-3m45-vv86-v3xh
Published 26-03-2026Last modified 27-07-2026

Vulnerability summary

CVE-2026-27893 is a high (CVSS 8.8) Protection Mechanism Failure vulnerability in vllm-project vllm. EPSS estimates a 1.81% chance of exploitation in the next 30 days, higher than 78.4% of scored vulnerabilities.

Overall risk
36/100
0100
Medium · default modelHow is this calculated?
CVSS score
8.8/10
010
High · v3.1 (CVE.org)
EPSS score
1.81%
0%100%
Low · +0.46 pp in 30 days
KEVNot listedNot listed by any tracked catalog.
RansomwareNot flaggedNo ransomware use recorded.
Public exploits0No public exploits recorded

Advisory lineage

Upstream 0 · Downstream 0 · Related 1

Timeline

  1. 26-03-2026
    PublishedVulnerability first disclosed.
  2. 27-07-2026
    Last modifiedVulnerability information updated.

Description

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.

CVSS metrics

4 scores · 4 sources · 1 version

EPSS trend

Probability

1.81%

Chance of exploitation in the next 30 days

Percentile

78%

Versus all other CVEs

30-day change

Increase +0.46 pp

From 1.35% on 22-09-2026

22-09-202622-10-2026

Known exploited

Compare KEV catalogs
CISA KEV

Not in the CISA KEV catalog.

ENISA CNW

Not in the ENISA CNW catalog.

CIRCL

Not in the CIRCL catalog.

Public exploits

0 found

No public exploits indexed.

Weaknesses

CWE · root cause

Affected systems

Chainguard5 products
  • py3.10-vllm-cuda-12.4< 0.18.1-r0
  • py3.12-vllm-cuda-12.4< 0.18.1-r0
  • tritonserver-backend-vllm-cuda-12.9All versions (No fix recorded)
  • tritonserver-backend-vllm-cuda-13.0< 25.11-r7
  • vllm-openai-cuda-12.9< 0.19.0-r0
PyPI1 product
  • vllm≥ 0.10.1, < 0.18.0
Vllm1 product
  • vllm≥ 0.10.1, < 0.18.0
Vllm-project1 product
  • vllm≥ 0.10.1, < 0.18.0

4 vendors · 8 products

References

21 links
Show all 21 references